Products
Customers
Company
Pricing
Resources
Introducing V7 Go

Solve tasks, reliably at scale.
Connect your data to GenAI workflows.

01

Connect your work to a reasoning engine

Any type of data
Automate workflows with foundation models that can reason across documents, images, and videos, with higher accuracy than calling a provider API directly.
Powered by the best frontier models
02

The fastest way to get started with AI

Instant setup, without API keys
Apply the latest foundation models to your data with no set up.
Chain models across your data
Connect multiple generative AI models to extract data, generate summaries, or perform complex reasoning tasks visually.
03

Improve reliability with human feedback

Human corrections
Improve risk assessment through automated analysis of financial statements and loan document verification.
Build trustworthy AI
Use conditional logic to route AI inference to humans in the loop for review.
01

Connect your work to a reasoning engine

Any type of data
Automate workflows with foundation models that can reason across documents, images, and videos, with higher accuracy than calling a provider API directly.
Powered by the best frontier models
02

The fastest way to get started with AI

Instant setup, without API keys
Apply the latest foundation models to your data with no set up.
Chain models across your data
Connect multiple generative AI models to extract data, generate summaries, or perform complex reasoning tasks visually.
03

Improve reliability with human feedback

Human corrections
Improve risk assessment through automated analysis of financial statements and loan document verification.
Build trustworthy AI
Use conditional logic to route AI inference to humans in the loop for review.
Use Cases

Build custom workflows to apply reasoning at scale.
GenAI automation, for thousands of use cases.

The Power of Go

How we reach 32% better accuracy than zero-shot RAG

The power behind V7 Go’s workflows is the ability to break down complex tasks into reasoning steps. Column by column, AI can reflect on parts of a problem rather than the whole, leading to a 32% reduction in errors over one-shot reasoning across document benchmarks, thanks to Chain of Thought Reasoning and Index Knowledge.
“V7 Go achieved 98% accuracy with a zero-shot approach using Index knowledge, against 66% and 42%.”
V7 Go is powered by Index Knowledge, a technology that breaks down large files containing information into small searchable indexes that enable LLMs to query information more accurately than retrieval augmented generation (RAG) techniques at the expense of more compute.
Traditional chat AI products simply inject text from documents into a prompt, whilst Index Knowledge utilizes the model itself to develop a data extraction plan, much like a human analyst would. This feature is particularly effective in files containing many numbers and uncommon terms such as proteins, proper nouns, and formulas, which RAG often fails to retrieve when summarizing.

We compared the extraction of these customs forms against two leading document processing providers, and achieved 98% accuracy with a zero-shot approach using Index knowledge, against 66% and 42%.
Alberto Rizzoli
Co-founder and CEO
Features

Run frontier models across your documents, images, text, and videos.

AI select properties
No more essay long answers. Enforce a discrete output with multi and single selects, making sure a model's output is constrained.
Build to integrate
A natural fit within your current stack, including API and JSON outputs for easy data management.
Visual grounding
Coming soon
Visualize the exact areas in your images or documents that AI-generated answers were based on.
Chain of thought
Connect multiple foundation models in sequences to automate complex tasks previously only humans could solve.
Index knowledge
Each document is turned into a database for AI to reason within. V7 Go automatically organizes text, tables, layout, and images, and allows the AI to use the best method to query them.
Workflows
Use conditional logic to create an AI powered assembly line. Branch your workflow to send your data through separate models with custom prompts or trigger extra steps for files passing or failing custom criteria.
Jade Yip
Product Manager
V7
Early V7 Go customers are building automations in days that previously would take teams of engineers to set up, and connected to internal AI tools to power them with LLMs.
Pricing
All prices are excluding VAT.
20% off on Pro annual payments.
Free
$0
/month
Get started
Fields
250
Go Tokens
50k
Properties
20
Seats
10
Workspaces
1
Pro
$249
/month
Get started
Fields
25,000
Go Tokens
1M
Properties
Unlimited
Seats
10
Workspaces
1
Extras
Command queue priority
Intercom chat support
Enterprise
Custom
Request a demo
Fields
Custom
Go Tokens
Custom
Properties
Unlimited
Seats
Custom
Workspaces
Custom
Extras
Command queue priority
Customer Success Manager
Bring your own key
SSO
Custom data retention
FAQ

Have questions?
Find answers.

Why should I use Go instead of calling a model provider directly?
Go is more accurate and robust than calling a model provider directly. By breaking down complex tasks into reasoning steps with Index Knowledge, Go enables LLMs to query your data more accurately than an out of the box API call. Combining this with conditional logic, which can route high sensitivity data to a human review, Go builds robustness into your AI powered workflows.
Is V7 Go part of V7 Darwin?
V7 Darwin is a data labeling platform for annotating videos and medical imaging to train your own model, while V7 Go specializes in applying foundation models to multimodal data, starting with intelligent document processing. In time they will be natively connected.
How do the limits of the Pro plan work?
The Pro plan is limited on fields (what you would call ‘cells’ in a spreadsheet) and Go tokens, which are consumed when you use AI models. The field limit does not refresh, while your token allowance resets on the same cadence as your billing cycle, either monthly of yearly. While both fields and tokens are a hard limit, they can be increased by expanding your plan.
What is a Go token?
Go tokens are standardized units obtained by converting tokens from various model providers into a single measure. More expensive models consume Go tokens at a faster rate than cheaper models. While Go tokens are metered and limited as part of a billing plan, the primary limit is on fields.
Does V7 Go support external models?
V7 Go will support external models via API, allowing for a flexible approach to document processing by incorporating both in-house and third-party AI models.
Can V7 Go recognize printed and handwritten text?
V7 Go is capable of recognizing both printed and handwritten text, leveraging advanced optical character recognition (OCR) technologies, as well as charts, diagrams and logos.
Brought to you by the V7 Go Team